Parts-of-Speech (English) Statistical NLP Spring Part-of-Speech Ambiguity. Why POS Tagging? Classic Solution: HMMs. Lecture 6: POS / Phrase MT
|
|
- Lenard Norton
- 5 years ago
- Views:
Transcription
1 Statistical LP Spring 2011 Lecture 6: POS / Phrase MT an Klein UC Berkeley Parts-of-Speech (English) One basic kind of linguistic structure: syntactic word classes Open class (lexical) words ouns Proper IBM Italy Common Closed class (functional) eterminers the some Conjunctions and or Pronouns cat / cats snow he its erbs Main see registered Modals can had Adjectives Adverbs umbers 122,312 one Prepositions Particles yellow slowly more to with off up more CC conjunction, coordinating and both but either or C numeral, cardinal mid-1890 nine-thirty 0.5 one T determiner a all an every no that the EX existential there there FW foreign word gemeinschaft hund ich jeux I preposition or conjunction, subordinating among whether out on by if adjective or numeral, ordinal third ill-mannered regrettable R adjective, comparative braver cheaper taller S adjective, superlative bravest cheapest tallest M modal auxiliary can may might will would noun, common, singular or mass cabbage thermostat investment subhumanity P noun, proper, singular Motown Cougar Yvette Liverpool PS noun, proper, plural Americans Materials States S noun, common, plural undergraduates bric-a-brac averages POS genitive marker ' 's PRP pronoun, personal hers himself it we them PRP pronoun, possessive her his mine my our ours their thy your RB adverb occasionally maddeningly adventurously RBR adverb, comparative further gloomier heavier less-perfectly RBS adverb, superlative best biggest nearest worst RP particle aboard away back by on open through TO "to" as preposition or infinitive marker to UH interjection huh howdy uh whammo shucks heck B verb, base form ask bring fire see take B verb, past tense pleaded swiped registered saw BG verb, present participle or gerund stirring focusing approaching erasing B verb, past participle dilapidated imitated reunifed unsettled BP verb, present tense, not 3rd person singular twist appear comprise mold postpone BZ verb, present tense, 3rd person singular bases reconstructs marks uses WT WH-determiner that what whatever which whichever WP WH-pronoun that what whatever which who whom WP WH-pronoun, possessive whose WRB Wh-adverb however whenever where why Part-of-Speech Ambiguity Words can have multiple parts of speech B B B BZ BP BZ P S S C Fed raises interest rates 0.5 percent Two basic sources of constraint: Grammatical environment Identity of the current word Many more possible features: Suffixes, capitalization, name databases (gazetteers), etc Why POS Tagging? Useful in and of itself (more than you d think) Text-to-speech: record, lead Lemmatization: saw[v] see, saw[n] saw Quick-and-dirty P-chunk detection: grep { }* { S} Useful as a pre-processing step for parsing Less tag ambiguity means fewer parses However, some tag choices are better decided by parsers I T P B B RP S The Georgia branch had taken on loan commitments T I B S B The average of interbank offered rates plummeted Classic Solution: HMMs We want a model of sequences s and observations w s 0 s 1 s 2 s n w 1 w 2 w n Assumptions: States are tag n-grams Usually a dedicated start and end state / word Tag/state sequence is generated by a markov model Words are chosen independently, conditioned only on the tag/state These are totally broken assumptions: why? 1
2 States States encode what is relevant about the past Transitions P(s s ) encode well-formed tag sequences In a bigram tagger, states = tags < > s 0 In a trigram tagger, states = tag pairs <, > < t 1> < t 2> < t n> s 1 s 2 s n w 1 w 2 w n <, t 1> < t 1, t 2> < t n-1, t n> Estimating Transitions Use standard smoothing methods to estimate transitions: P( ti ti 1, ti 2) = λ2pˆ( ti ti 1, ti 2) + λ1pˆ( ti ti 1) + (1 λ1 λ2 ) Pˆ( ti ) Can get a lot fancier (e.g. K smoothing) or use higher orders, but in this case it doesn t buy much One option: encode more into the state, e.g. whether the previous word was capitalized (Brants 00) BIG IEA: The basic approach of state-splitting turns out to be very important in a range of tasks s 0 s 1 s 2 s n w 1 w 2 w n Estimating Emissions isambiguation (Inference) Problem: find the most likely (iterbi) sequence under the model Emissions are trickier: Words we ve never seen before Words which occur with tags we ve never seen them with One option: break out the Good-Turning smoothing Issue: unknown words aren t black boxes: 343, year Minteria reintroducibly Basic solution: unknown words classes (affixes or shapes) +, x + Xx + x + - ly [Brants 00] used a suffix trie as its emission model Given model parameters, we can score any tag sequence <, > <,P> <P, BZ> <BZ, > <, S> <S, C> <C, > <STOP> P BZ S C. Fed raises interest rates 0.5 percent. P(P <, >) P(Fed P) P(BZ <P, >) P(raises BZ) P( BZ,P).. In principle, we re done list all possible tag sequences, score each one, pick the best one (the iterbi state sequence) P BZ S C P S S C P BZ B S C logp = -23 logp = -29 logp = -27 Finding the Best Trajectory The State Lattice / Trellis Too many trajectories (state sequences) to list Option 1: Beam Search Fed:P Fed:P raises:s <> Fed:B Fed:P raises:bz Fed:B raises:s Fed:B Fed:B raises:bz A beam is a set of partial hypotheses Start with just the single empty trajectory At each derivation step: Consider all continuations of previous hypotheses iscard most, keep top k, or those within a factor of the best Beam search works ok in practice but sometimes you want the optimal answer and you need optimal answers to validate your beam search and there s usually a better option than naïve beams START Fed raises interest rates E 2
3 The State Lattice / Trellis START Fed raises interest rates E The iterbi Algorithm ynamic program for computing δi( s) = max P( s0... s 1, ) 0... i s w wi s si 1s The score of a best path up to position i ending in state s δi( s) = max P( s s' ) P( w s' ) δi 1( s' ) s' Also can store a backtrace (but no one does) Memoized solution Iterative solution 1 if s =<, > δ 0 ( s) = 0 otherwise ψ s) = arg max P( s s' ) P( w s' ) δ ( s' ) i( i 1 s' So How Well oes It Work? Choose the most common tag 90.3% with a bad unknown word model 93.7% with a good one Overview: Accuracies Roadmap of (known / unknown) accuracies: Most freq tag: ~90% / ~50% TnT (Brants, 2000): A carefully smoothed trigram tagger Suffix trees for emissions 96.7% on WS text (SOA is ~97.5%) oise in the data Many errors in the training and test corpora T I B S B The average of interbank offered rates plummeted Probably about 2% guaranteed error from noise (on this data) Trigram HMM: ~95% / ~55% TnT (HMM++): 96.2% / 86.0% Maxent P(t w): 93.7% / 82.6% MEMM tagger: 96.9% / 86.9% Cyclic tagger: 97.2% / 89.0% Upper bound: ~98% Most errors on unknown words Common Errors Common errors [from Toutanova & Manning 00] Corpus-Based MT Modeling correspondences between languages Sentence-aligned parallel corpus: Yo lo haré mañana I will do it tomorrow Hasta pronto See you soon Hasta pronto See you around Machine translation system: Yo lo haré pronto Model of translation I will do it soon I will do it around / official knowledge B RP/I T made up the story RB B/B S recently sold shares See you tomorrow 3
4 Phrase-Based Systems Sentence-aligned corpus Word alignments cat chat 0.9 the cat le chat 0.8 dog chien 0.8 house maison 0.6 my house ma maison 0.9 language langue 0.9 Phrase table (translation model) Many slides and examples from Philipp Koehn or ohn eero Phrase-Based ecoding The Pharaoh Model 这 7 人中包括来自法国和俄罗斯的宇航员. [Koehn et al, 2003] Segmentation Translation istortion ecoder design is important: [Koehn et al. 03] The Pharaoh Model Phrase Weights Where do we get these counts? 4
5 Phrase-Based ecoding Monotonic Word Translation Cost is LM * TM It s an HMM? P(e e -1,e -2 ) P(f e) State includes Exposed English Position in foreign ynamic program loop? [. a slap, 5] [. slap to, 6] [. slap by, 6] for (fposition in 1 f ) for (econtext in allecontexts) for (eoption in translations[fposition]) score = scores[fposition-1][econtext] * LM(eContext) * TM(eOption, fword[fposition]) scores[fposition][econtext[2]+eoption] = max score Beam ecoding Phrase Translation For real MT models, this kind of dynamic program is a disaster (why?) Standard solution is beam search: for each position, keep track of only the best k hypotheses for (fposition in 1 f ) for (econtext in bestecontexts[fposition]) for (eoption in translations[fposition]) score = scores[fposition-1][econtext] * LM(eContext) * TM(eOption, fword[fposition]) bestecontexts.maybeadd(econtext[2]+eoption, score) Still pretty slow why? Useful trick: cube pruning (Chiang 2005) If monotonic, almost an HMM; technically a semi-hmm for (fposition in 1 f ) for (lastposition < fposition) for (econtext in econtexts) for (eoption in translations[fposition]) combine hypothesis for (lastposition ending in econtext) with eoption If distortion now what? Example from avid Chiang on-monotonic Phrasal MT Pruning: Beams + Forward Costs Problem: easy partial analyses are cheaper Solution 1: use beams per foreign subset Solution 2: estimate forward costs (A*-like) 5
6 The Pharaoh ecoder Hypotheis Lattices 6
Statistical NLP Spring Parts-of-Speech (English)
Statistical LP Spring 2009 Lecture 6: Parts-of-Speech an Klein UC Berkeley Parts-of-Speech (English) One basic kind of linguistic structure: syntactic word classes Open class (lexical) words ouns erbs
More informationCSE 490 U Natural Language Processing Spring 2016
CSE 490 U atural Language Processing Spring 2016 Parts of Speech Yejin Choi [Slides adapted from an Klein, Luke Zettlemoyer] Overview POS Tagging Feature Rich Techniques Maximum Entropy Markov Models (MEMMs)
More informationNatural Language Processing
Natural Language Processing Part of Speech Tagging Dan Klein UC Berkeley 1 Parts of Speech 2 Parts of Speech (English) One basic kind of linguistic structure: syntactic word classes Open class (lexical)
More informationAlgorithms for NLP. Machine Translation II. Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley
Algorithms for NLP Machine Translation II Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley Announcements Project 4: Word Alignment! Will be released soon! (~Monday) Phrase-Based System Overview
More informationLECTURER: BURCU CAN Spring
LECTURER: BURCU CAN 2018-2019 Spring Open class (lexical) words Nouns Verbs Adjectives yellow Proper Common Main Adverbs slowly IBM Italy cat / cats snow see registered Numbers more 122,312 Closed class
More informationStatistical NLP Spring Corpus-Based MT
Statistical NLP Spring 2010 Lecture 17: Word / Phrase MT Dan Klein UC Berkeley Corpus-Based MT Modeling correspondences between languages Sentence-aligned parallel corpus: Yo lo haré mañana I will do it
More informationCorpus-Based MT. Statistical NLP Spring Unsupervised Word Alignment. Alignment Error Rate. IBM Models 1/2. Problems with Model 1
Statistical NLP Spring 2010 Corpus-Based MT Modeling correspondences between languages Sentence-aligned parallel corpus: Yo lo haré mañana I will do it tomorrow Hasta pronto See you soon Hasta pronto See
More informationCSE 517 Natural Language Processing Winter2015
CSE 517 Natural Language Processing Winter2015 Feature Rich Models Sameer Singh Guest lecture for Yejin Choi - University of Washington [Slides from Jason Eisner, Dan Klein, Luke ZeLlemoyer] Outline POS
More informationSequence Prediction and Part-of-speech Tagging
CS5740: atural Language Processing Spring 2017 Sequence Prediction and Part-of-speech Tagging Instructor: Yoav Artzi Slides adapted from Dan Klein, Dan Jurafsky, Chris Manning, Michael Collins, Luke Zettlemoyer,
More information10/17/04. Today s Main Points
Part-of-speech Tagging & Hidden Markov Model Intro Lecture #10 Introduction to Natural Language Processing CMPSCI 585, Fall 2004 University of Massachusetts Amherst Andrew McCallum Today s Main Points
More informationTime Zones - KET Grammar
Inventory of grammatical areas Verbs Regular and irregular forms Pages 104-105 (Unit 1 Modals can (ability; requests; permission) could (ability; polite requests) Page 3 (Getting Started) Pages 45-47,
More informationEmpirical Methods in Natural Language Processing Lecture 11 Part-of-speech tagging and HMMs
Empirical Methods in Natural Language Processing Lecture 11 Part-of-speech tagging and HMMs (based on slides by Sharon Goldwater and Philipp Koehn) 21 February 2018 Nathan Schneider ENLP Lecture 11 21
More informationLecture 12: Algorithms for HMMs
Lecture 12: Algorithms for HMMs Nathan Schneider (some slides from Sharon Goldwater; thanks to Jonathan May for bug fixes) ENLP 26 February 2018 Recap: tagging POS tagging is a sequence labelling task.
More informationLecture 12: Algorithms for HMMs
Lecture 12: Algorithms for HMMs Nathan Schneider (some slides from Sharon Goldwater; thanks to Jonathan May for bug fixes) ENLP 17 October 2016 updated 9 September 2017 Recap: tagging POS tagging is a
More informationHidden Markov Models
CS 2750: Machine Learning Hidden Markov Models Prof. Adriana Kovashka University of Pittsburgh March 21, 2016 All slides are from Ray Mooney Motivating Example: Part Of Speech Tagging Annotate each word
More informationPosterior vs. Parameter Sparsity in Latent Variable Models Supplementary Material
Posterior vs. Parameter Sparsity in Latent Variable Models Supplementary Material João V. Graça L 2 F INESC-ID Lisboa, Portugal Kuzman Ganchev Ben Taskar University of Pennsylvania Philadelphia, PA, USA
More informationHidden Markov Models (HMMs)
Hidden Markov Models HMMs Raymond J. Mooney University of Texas at Austin 1 Part Of Speech Tagging Annotate each word in a sentence with a part-of-speech marker. Lowest level of syntactic analysis. John
More informationINF4820: Algorithms for Artificial Intelligence and Natural Language Processing. Hidden Markov Models
INF4820: Algorithms for Artificial Intelligence and Natural Language Processing Hidden Markov Models Murhaf Fares & Stephan Oepen Language Technology Group (LTG) October 18, 2017 Recap: Probabilistic Language
More informationNatural Language Processing Winter 2013
Natural Language Processing Winter 2013 Hidden Markov Models Luke Zettlemoyer - University of Washington [Many slides from Dan Klein and Michael Collins] Overview Hidden Markov Models Learning Supervised:
More informationLatent Variable Models in NLP
Latent Variable Models in NLP Aria Haghighi with Slav Petrov, John DeNero, and Dan Klein UC Berkeley, CS Division Latent Variable Models Latent Variable Models Latent Variable Models Observed Latent Variable
More informationINF4820: Algorithms for Artificial Intelligence and Natural Language Processing. Hidden Markov Models
INF4820: Algorithms for Artificial Intelligence and Natural Language Processing Hidden Markov Models Murhaf Fares & Stephan Oepen Language Technology Group (LTG) October 27, 2016 Recap: Probabilistic Language
More informationACS Introduction to NLP Lecture 2: Part of Speech (POS) Tagging
ACS Introduction to NLP Lecture 2: Part of Speech (POS) Tagging Stephen Clark Natural Language and Information Processing (NLIP) Group sc609@cam.ac.uk The POS Tagging Problem 2 England NNP s POS fencers
More informationStatistical methods in NLP, lecture 7 Tagging and parsing
Statistical methods in NLP, lecture 7 Tagging and parsing Richard Johansson February 25, 2014 overview of today's lecture HMM tagging recap assignment 3 PCFG recap dependency parsing VG assignment 1 overview
More informationCSE 490 U Natural Language Processing Spring 2016
CSE 490 U Natural Language Processing Spring 2016 Feature Rich Models Yejin Choi - University of Washington [Many slides from Dan Klein, Luke Zettlemoyer] Structure in the output variable(s)? What is the
More informationPart of Speech Tagging: Viterbi, Forward, Backward, Forward- Backward, Baum-Welch. COMP-599 Oct 1, 2015
Part of Speech Tagging: Viterbi, Forward, Backward, Forward- Backward, Baum-Welch COMP-599 Oct 1, 2015 Announcements Research skills workshop today 3pm-4:30pm Schulich Library room 313 Start thinking about
More informationHidden Markov Models in Language Processing
Hidden Markov Models in Language Processing Dustin Hillard Lecture notes courtesy of Prof. Mari Ostendorf Outline Review of Markov models What is an HMM? Examples General idea of hidden variables: implications
More informationNatural Language Processing Prof. Pawan Goyal Department of Computer Science and Engineering Indian Institute of Technology, Kharagpur
Natural Language Processing Prof. Pawan Goyal Department of Computer Science and Engineering Indian Institute of Technology, Kharagpur Lecture - 18 Maximum Entropy Models I Welcome back for the 3rd module
More informationMachine Translation: Examples. Statistical NLP Spring Levels of Transfer. Corpus-Based MT. World-Level MT: Examples
Statistical NLP Spring 2009 Machine Translation: Examples Lecture 17: Word Alignment Dan Klein UC Berkeley Corpus-Based MT Levels of Transfer Modeling correspondences between languages Sentence-aligned
More informationNatural Language Processing (CSE 517): Sequence Models (II)
Natural Language Processing (CSE 517): Sequence Models (II) Noah Smith c 2016 University of Washington nasmith@cs.washington.edu February 3, 2016 1 / 40 Full Viterbi Procedure Input: x, θ, γ, π Output:
More informationCOMP (Fall 2017) Natural Language Processing (with deep learning and connections to vision/robotics)
COMP 790.139 (Fall 2017) Natural Language Processing (with deep learning and connections to vision/robotics) Lecture 3: POS-Tagging, NER, Seq Labeling, Coreference Mohit Bansal (various slides adapted/borrowed
More informationHMM and Part of Speech Tagging. Adam Meyers New York University
HMM and Part of Speech Tagging Adam Meyers New York University Outline Parts of Speech Tagsets Rule-based POS Tagging HMM POS Tagging Transformation-based POS Tagging Part of Speech Tags Standards There
More informationNatural Language Processing (CSE 517): Sequence Models
Natural Language Processing (CSE 517): Sequence Models Noah Smith c 2018 University of Washington nasmith@cs.washington.edu April 27, 2018 1 / 60 High-Level View of Viterbi The decision about Y l is a
More informationFun with weighted FSTs
Fun with weighted FSTs Informatics 2A: Lecture 18 Shay Cohen School of Informatics University of Edinburgh 29 October 2018 1 / 35 Kedzie et al. (2018) - Content Selection in Deep Learning Models of Summarization
More informationN-grams. Motivation. Simple n-grams. Smoothing. Backoff. N-grams L545. Dept. of Linguistics, Indiana University Spring / 24
L545 Dept. of Linguistics, Indiana University Spring 2013 1 / 24 Morphosyntax We just finished talking about morphology (cf. words) And pretty soon we re going to discuss syntax (cf. sentences) In between,
More informationINF4820: Algorithms for Artificial Intelligence and Natural Language Processing. Language Models & Hidden Markov Models
1 University of Oslo : Department of Informatics INF4820: Algorithms for Artificial Intelligence and Natural Language Processing Language Models & Hidden Markov Models Stephan Oepen & Erik Velldal Language
More informationA Syntax-based Statistical Machine Translation Model. Alexander Friedl, Georg Teichtmeister
A Syntax-based Statistical Machine Translation Model Alexander Friedl, Georg Teichtmeister 4.12.2006 Introduction The model Experiment Conclusion Statistical Translation Model (STM): - mathematical model
More informationPart-of-Speech Tagging + Neural Networks CS 287
Part-of-Speech Tagging + Neural Networks CS 287 Quiz Last class we focused on hinge loss. L hinge = max{0, 1 (ŷ c ŷ c )} Consider now the squared hinge loss, (also called l 2 SVM) L hinge 2 = max{0, 1
More informationDecoding in Statistical Machine Translation. Mid-course Evaluation. Decoding. Christian Hardmeier
Decoding in Statistical Machine Translation Christian Hardmeier 2016-05-04 Mid-course Evaluation http://stp.lingfil.uu.se/~sara/kurser/mt16/ mid-course-eval.html Decoding The decoder is the part of the
More informationMidterm sample questions
Midterm sample questions CS 585, Brendan O Connor and David Belanger October 12, 2014 1 Topics on the midterm Language concepts Translation issues: word order, multiword translations Human evaluation Parts
More informationCSE 447/547 Natural Language Processing Winter 2018
CSE 447/547 Natural Language Processing Winter 2018 Feature Rich Models (Log Linear Models) Yejin Choi University of Washington [Many slides from Dan Klein, Luke Zettlemoyer] Announcements HW #3 Due Feb
More informationLecture 13: Structured Prediction
Lecture 13: Structured Prediction Kai-Wei Chang CS @ University of Virginia kw@kwchang.net Couse webpage: http://kwchang.net/teaching/nlp16 CS6501: NLP 1 Quiz 2 v Lectures 9-13 v Lecture 12: before page
More informationPart-of-Speech Tagging
Part-of-Speech Tagging Informatics 2A: Lecture 17 Adam Lopez School of Informatics University of Edinburgh 27 October 2016 1 / 46 Last class We discussed the POS tag lexicon When do words belong to the
More informationThe Noisy Channel Model and Markov Models
1/24 The Noisy Channel Model and Markov Models Mark Johnson September 3, 2014 2/24 The big ideas The story so far: machine learning classifiers learn a function that maps a data item X to a label Y handle
More informationNatural Language Processing CS Lecture 06. Razvan C. Bunescu School of Electrical Engineering and Computer Science
Natural Language Processing CS 6840 Lecture 06 Razvan C. Bunescu School of Electrical Engineering and Computer Science bunescu@ohio.edu Statistical Parsing Define a probabilistic model of syntax P(T S):
More informationMaschinelle Sprachverarbeitung
Maschinelle Sprachverarbeitung Parsing with Probabilistic Context-Free Grammar Ulf Leser Content of this Lecture Phrase-Structure Parse Trees Probabilistic Context-Free Grammars Parsing with PCFG Other
More informationTnT Part of Speech Tagger
TnT Part of Speech Tagger By Thorsten Brants Presented By Arghya Roy Chaudhuri Kevin Patel Satyam July 29, 2014 1 / 31 Outline 1 Why Then? Why Now? 2 Underlying Model Other technicalities 3 Evaluation
More informationMaschinelle Sprachverarbeitung
Maschinelle Sprachverarbeitung Parsing with Probabilistic Context-Free Grammar Ulf Leser Content of this Lecture Phrase-Structure Parse Trees Probabilistic Context-Free Grammars Parsing with PCFG Other
More informationNatural Language Processing SoSe Words and Language Model
Natural Language Processing SoSe 2016 Words and Language Model Dr. Mariana Neves May 2nd, 2016 Outline 2 Words Language Model Outline 3 Words Language Model Tokenization Separation of words in a sentence
More informationCS388: Natural Language Processing Lecture 4: Sequence Models I
CS388: Natural Language Processing Lecture 4: Sequence Models I Greg Durrett Mini 1 due today Administrivia Project 1 out today, due September 27 Viterbi algorithm, CRF NER system, extension Extension
More informationA Context-Free Grammar
Statistical Parsing A Context-Free Grammar S VP VP Vi VP Vt VP VP PP DT NN PP PP P Vi sleeps Vt saw NN man NN dog NN telescope DT the IN with IN in Ambiguity A sentence of reasonable length can easily
More informationRecap: Language models. Foundations of Natural Language Processing Lecture 4 Language Models: Evaluation and Smoothing. Two types of evaluation in NLP
Recap: Language models Foundations of atural Language Processing Lecture 4 Language Models: Evaluation and Smoothing Alex Lascarides (Slides based on those from Alex Lascarides, Sharon Goldwater and Philipp
More informationSequences and Information
Sequences and Information Rahul Siddharthan The Institute of Mathematical Sciences, Chennai, India http://www.imsc.res.in/ rsidd/ Facets 16, 04/07/2016 This box says something By looking at the symbols
More informationCS838-1 Advanced NLP: Hidden Markov Models
CS838-1 Advanced NLP: Hidden Markov Models Xiaojin Zhu 2007 Send comments to jerryzhu@cs.wisc.edu 1 Part of Speech Tagging Tag each word in a sentence with its part-of-speech, e.g., The/AT representative/nn
More informationStatistical NLP Spring HW2: PNP Classification
Statistical NLP Spring 2010 Lecture 16: Word Alignment Dan Klein UC Berkeley HW2: PNP Classification Overall: good work! Top results: 88.1: Matthew Can (word/phrase pre/suffixes) 88.1: Kurtis Heimerl (positional
More informationHW2: PNP Classification. Statistical NLP Spring Levels of Transfer. Phrasal / Syntactic MT: Examples. Lecture 16: Word Alignment
Statistical NLP Spring 2010 Lecture 16: Word Alignment Dan Klein UC Berkeley HW2: PNP Classification Overall: good work! Top results: 88.1: Matthew Can (word/phrase pre/suffixes) 88.1: Kurtis Heimerl (positional
More informationLECTURER: BURCU CAN Spring
LECTURER: BURCU CAN 2017-2018 Spring Regular Language Hidden Markov Model (HMM) Context Free Language Context Sensitive Language Probabilistic Context Free Grammar (PCFG) Unrestricted Language PCFGs can
More informationPOS-Tagging. Fabian M. Suchanek
POS-Tagging Fabian M. Suchanek 100 Def: POS A Part-of-Speech (also: POS, POS-tag, word class, lexical class, lexical category) is a set of words with the same grammatical role. Alizée wrote a really great
More informationNeural POS-Tagging with Julia
Neural POS-Tagging with Julia Hiroyuki Shindo 2015-12-19 Julia Tokyo Why Julia? NLP の基礎解析 ( 研究レベル ) ベクトル演算以外の計算も多い ( 探索など ) Java, Scala, C++ Python-like な文法で, 高速なプログラミング言語 Julia, Nim, Crystal? 1 Part-of-Speech
More informationIBM Model 1 for Machine Translation
IBM Model 1 for Machine Translation Micha Elsner March 28, 2014 2 Machine translation A key area of computational linguistics Bar-Hillel points out that human-like translation requires understanding of
More informationCSE 447 / 547 Natural Language Processing Winter 2018
CSE 447 / 547 Natural Language Processing Winter 2018 Hidden Markov Models Yejin Choi University of Washington [Many slides from Dan Klein, Michael Collins, Luke Zettlemoyer] Overview Hidden Markov Models
More informationLING 473: Day 10. START THE RECORDING Coding for Probability Hidden Markov Models Formal Grammars
LING 473: Day 10 START THE RECORDING Coding for Probability Hidden Markov Models Formal Grammars 1 Issues with Projects 1. *.sh files must have #!/bin/sh at the top (to run on Condor) 2. If run.sh is supposed
More informationStatistical Methods for NLP
Statistical Methods for NLP Sequence Models Joakim Nivre Uppsala University Department of Linguistics and Philology joakim.nivre@lingfil.uu.se Statistical Methods for NLP 1(21) Introduction Structured
More informationStatistical Machine Translation. Part III: Search Problem. Complexity issues. DP beam-search: with single and multi-stacks
Statistical Machine Translation Marcello Federico FBK-irst Trento, Italy Galileo Galilei PhD School - University of Pisa Pisa, 7-19 May 008 Part III: Search Problem 1 Complexity issues A search: with single
More information(7) a. [ PP to John], Mary gave the book t [PP]. b. [ VP fix the car], I wonder whether she will t [VP].
CAS LX 522 Syntax I Fall 2000 September 18, 2000 Paul Hagstrom Week 2: Movement Movement Last time, we talked about subcategorization. (1) a. I can solve this problem. b. This problem, I can solve. (2)
More informationStructured Output Prediction: Generative Models
Structured Output Prediction: Generative Models CS6780 Advanced Machine Learning Spring 2015 Thorsten Joachims Cornell University Reading: Murphy 17.3, 17.4, 17.5.1 Structured Output Prediction Supervised
More informationPart A. P (w 1 )P (w 2 w 1 )P (w 3 w 1 w 2 ) P (w M w 1 w 2 w M 1 ) P (w 1 )P (w 2 w 1 )P (w 3 w 2 ) P (w M w M 1 )
Part A 1. A Markov chain is a discrete-time stochastic process, defined by a set of states, a set of transition probabilities (between states), and a set of initial state probabilities; the process proceeds
More informationNatural Language Processing SoSe Language Modelling. (based on the slides of Dr. Saeedeh Momtazi)
Natural Language Processing SoSe 2015 Language Modelling Dr. Mariana Neves April 20th, 2015 (based on the slides of Dr. Saeedeh Momtazi) Outline 2 Motivation Estimation Evaluation Smoothing Outline 3 Motivation
More informationProbabilistic Graphical Models
CS 1675: Intro to Machine Learning Probabilistic Graphical Models Prof. Adriana Kovashka University of Pittsburgh November 27, 2018 Plan for This Lecture Motivation for probabilistic graphical models Directed
More informationConditional Language Modeling. Chris Dyer
Conditional Language Modeling Chris Dyer Unconditional LMs A language model assigns probabilities to sequences of words,. w =(w 1,w 2,...,w`) It is convenient to decompose this probability using the chain
More informationN-gram Language Modeling Tutorial
N-gram Language Modeling Tutorial Dustin Hillard and Sarah Petersen Lecture notes courtesy of Prof. Mari Ostendorf Outline: Statistical Language Model (LM) Basics n-gram models Class LMs Cache LMs Mixtures
More informationLog-Linear Models, MEMMs, and CRFs
Log-Linear Models, MEMMs, and CRFs Michael Collins 1 Notation Throughout this note I ll use underline to denote vectors. For example, w R d will be a vector with components w 1, w 2,... w d. We use expx
More informationMaxent Models and Discriminative Estimation
Maxent Models and Discriminative Estimation Generative vs. Discriminative models (Reading: J+M Ch6) Introduction So far we ve looked at generative models Language models, Naive Bayes But there is now much
More informationNatural Language Processing : Probabilistic Context Free Grammars. Updated 5/09
Natural Language Processing : Probabilistic Context Free Grammars Updated 5/09 Motivation N-gram models and HMM Tagging only allowed us to process sentences linearly. However, even simple sentences require
More informationHidden Markov Models
Hidden Markov Models Slides mostly from Mitch Marcus and Eric Fosler (with lots of modifications). Have you seen HMMs? Have you seen Kalman filters? Have you seen dynamic programming? HMMs are dynamic
More informationDecoding and Inference with Syntactic Translation Models
Decoding and Inference with Syntactic Translation Models March 5, 2013 CFGs S NP VP VP NP V V NP NP CFGs S NP VP S VP NP V V NP NP CFGs S NP VP S VP NP V NP VP V NP NP CFGs S NP VP S VP NP V NP VP V NP
More informationLecture 4: Smoothing, Part-of-Speech Tagging. Ivan Titov Institute for Logic, Language and Computation Universiteit van Amsterdam
Lecture 4: Smoothing, Part-of-Speech Tagging Ivan Titov Institute for Logic, Language and Computation Universiteit van Amsterdam Language Models from Corpora We want a model of sentence probability P(w
More informationLecture 7: Sequence Labeling
http://courses.engr.illinois.edu/cs447 Lecture 7: Sequence Labeling Julia Hockenmaier juliahmr@illinois.edu 3324 Siebel Center Recap: Statistical POS tagging with HMMs (J. Hockenmaier) 2 Recap: Statistical
More informationLecture 15. Probabilistic Models on Graph
Lecture 15. Probabilistic Models on Graph Prof. Alan Yuille Spring 2014 1 Introduction We discuss how to define probabilistic models that use richly structured probability distributions and describe how
More informationLexical Translation Models 1I. January 27, 2015
Lexical Translation Models 1I January 27, 2015 Last Time... X p( Translation)= p(, Translation) Alignment = X Alignment Alignment p( p( Alignment) Translation Alignment) {z } {z } X z } { z } { p(e f,m)=
More informationDual Decomposition for Natural Language Processing. Decoding complexity
Dual Decomposition for atural Language Processing Alexander M. Rush and Michael Collins Decoding complexity focus: decoding problem for natural language tasks motivation: y = arg max y f (y) richer model
More informationSpatial Role Labeling CS365 Course Project
Spatial Role Labeling CS365 Course Project Amit Kumar, akkumar@iitk.ac.in Chandra Sekhar, gchandra@iitk.ac.in Supervisor : Dr.Amitabha Mukerjee ABSTRACT In natural language processing one of the important
More information> > > > < 0.05 θ = 1.96 = 1.64 = 1.66 = 0.96 = 0.82 Geographical distribution of English tweets (gender-induced data) Proportion of gendered tweets in English, May 2016 1 Contexts of the Present Research
More informationLecture 6: Part-of-speech tagging
CS447: Natural Language Processing http://courses.engr.illinois.edu/cs447 Lecture 6: Part-of-speech tagging Julia Hockenmaier juliahmr@illinois.edu 3324 Siebel Center Smoothing: Reserving mass in P(X Y)
More informationMachine Translation. CL1: Jordan Boyd-Graber. University of Maryland. November 11, 2013
Machine Translation CL1: Jordan Boyd-Graber University of Maryland November 11, 2013 Adapted from material by Philipp Koehn CL1: Jordan Boyd-Graber (UMD) Machine Translation November 11, 2013 1 / 48 Roadmap
More informationNatural Language Processing
SFU NatLangLab Natural Language Processing Anoop Sarkar anoopsarkar.github.io/nlp-class Simon Fraser University October 9, 2018 0 Natural Language Processing Anoop Sarkar anoopsarkar.github.io/nlp-class
More informationDiscriminative Training. March 4, 2014
Discriminative Training March 4, 2014 Noisy Channels Again p(e) source English Noisy Channels Again p(e) p(g e) source English German Noisy Channels Again p(e) p(g e) source English German decoder e =
More informationMODERN VIDYA NIKETAN SCHOOL ENTRANCE TEST SYLLABUS FOR KG ( )
FOR KG (K.G.) A T 1. Write in Sequence. 2. Dictation / Drill 3. Match the Capital with Cursive Letters. 4. Match the picture with letter. 5. Complete the series. ( Missing Letters ) MATHS ( K.G.) 1 30
More informationCS 224N HW:#3. (V N0 )δ N r p r + N 0. N r (r δ) + (V N 0)δ. N r r δ. + (V N 0)δ N = 1. 1 we must have the restriction: δ NN 0.
CS 224 HW:#3 ARIA HAGHIGHI SUID :# 05041774 1. Smoothing Probability Models (a). Let r be the number of words with r counts and p r be the probability for a word with r counts in the Absolute discounting
More informationN-gram Language Modeling
N-gram Language Modeling Outline: Statistical Language Model (LM) Intro General N-gram models Basic (non-parametric) n-grams Class LMs Mixtures Part I: Statistical Language Model (LM) Intro What is a statistical
More informationQuiz 1, COMS Name: Good luck! 4705 Quiz 1 page 1 of 7
Quiz 1, COMS 4705 Name: 10 30 30 20 Good luck! 4705 Quiz 1 page 1 of 7 Part #1 (10 points) Question 1 (10 points) We define a PCFG where non-terminal symbols are {S,, B}, the terminal symbols are {a, b},
More informationToday s Agenda. Need to cover lots of background material. Now on to the Map Reduce stuff. Rough conceptual sketch of unsupervised training using EM
Today s Agenda Need to cover lots of background material l Introduction to Statistical Models l Hidden Markov Models l Part of Speech Tagging l Applying HMMs to POS tagging l Expectation-Maximization (EM)
More information1. Markov models. 1.1 Markov-chain
1. Markov models 1.1 Markov-chain Let X be a random variable X = (X 1,..., X t ) taking values in some set S = {s 1,..., s N }. The sequence is Markov chain if it has the following properties: 1. Limited
More informationLanguage Models. Data Science: Jordan Boyd-Graber University of Maryland SLIDES ADAPTED FROM PHILIP KOEHN
Language Models Data Science: Jordan Boyd-Graber University of Maryland SLIDES ADAPTED FROM PHILIP KOEHN Data Science: Jordan Boyd-Graber UMD Language Models 1 / 8 Language models Language models answer
More informationParsing with Context-Free Grammars
Parsing with Context-Free Grammars Berlin Chen 2005 References: 1. Natural Language Understanding, chapter 3 (3.1~3.4, 3.6) 2. Speech and Language Processing, chapters 9, 10 NLP-Berlin Chen 1 Grammars
More informationCS 188: Artificial Intelligence Fall 2011
CS 188: Artificial Intelligence Fall 2011 Lecture 20: HMMs / Speech / ML 11/8/2011 Dan Klein UC Berkeley Today HMMs Demo bonanza! Most likely explanation queries Speech recognition A massive HMM! Details
More informationNatural Language Processing 1. lecture 7: constituent parsing. Ivan Titov. Institute for Logic, Language and Computation
atural Language Processing 1 lecture 7: constituent parsing Ivan Titov Institute for Logic, Language and Computation Outline Syntax: intro, CFGs, PCFGs PCFGs: Estimation CFGs: Parsing PCFGs: Parsing Parsing
More informationAccelerated Natural Language Processing Lecture 3 Morphology and Finite State Machines; Edit Distance
Accelerated Natural Language Processing Lecture 3 Morphology and Finite State Machines; Edit Distance Sharon Goldwater (based on slides by Philipp Koehn) 20 September 2018 Sharon Goldwater ANLP Lecture
More informationNatural Language Processing
SFU NatLangLab Natural Language Processing Anoop Sarkar anoopsarkar.github.io/nlp-class Simon Fraser University September 27, 2018 0 Natural Language Processing Anoop Sarkar anoopsarkar.github.io/nlp-class
More informationPhrase-Based Statistical Machine Translation with Pivot Languages
Phrase-Based Statistical Machine Translation with Pivot Languages N. Bertoldi, M. Barbaiani, M. Federico, R. Cattoni FBK, Trento - Italy Rovira i Virgili University, Tarragona - Spain October 21st, 2008
More informationAlgorithms for NLP. Language Modeling III. Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley
Algorithms for NLP Language Modeling III Taylor Berg-Kirkpatrick CMU Slides: Dan Klein UC Berkeley Announcements Office hours on website but no OH for Taylor until next week. Efficient Hashing Closed address
More information